الباحثون

Minghong Fang

المنشورات 2

نسخة أولية وصول مفتوح

Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

Omar Sheta, Rinku Deuja, Hadi Masoudi وآخرون · 2026

Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single prompts: they score an input by the alignment between its induced …

نسخة أولية وصول مفتوح

Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning

Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu وآخرون · 2026

Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack surface: a small amount of harmful data mixed into an otherwise benign fine-tuning set can degrade the model's alignment. Two recent alignment-stage defenses address this problem …

المؤلفون المشاركون